Skip to main content

How can I identify a ROI that is formed by many contours (canny image)? (OpenCV and Python)

I'm newbie with OpenCV, but I'm tring to do a solution to identify flaws in a machining process in a specific Region of Interrest (ROI).

I wrote a code that can 'identify' this ROI and ignores the rest of the part, however I don't know how to create a filter in that region, because my Canny image is formed by a lot of small areas, and not by a single area.

What I want to do, is find a way to get ROI's bounding box (x,y,w,h) coordinates for after filter my input (webcam) image with this ROI and apply again the Canny method to identify this machining flaws

I put my code and a image from the metal part and the Canny image showing the ROI. I've never use computer vision so I'd be very grateful if someone helps me.

def getContours(img):
contours, Hierarchy = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
for i in contours:
    area = cv2.contourArea(i)
    # print(area)
    if area>500:
        cv2.drawContours(img, i, -1, (255, 0, 0), 3)

return img


def empty(a):
    pass


def detect_cont(img, pos_min, pos_max):
    imgGray = convert_gray(img)
    imgBlur = cv2.GaussianBlur(imgGray,(7,7),1)
    imgContours = img.copy()
    imgCanny = cv2.Canny(imgBlur, pos_min, pos_max)  # 200,0

imgContours = getContours(imgCanny)

return imgCanny, imgContours

#cv2.imshow("Image", imgBlur)
#cv2.imshow("ImageCanny", imgCanny)
#cv2.waitKey(0)


if __name__ == '__main__':

#use_webcam()
#img = reading_image("Bad1.jpg")
#reading_video("")

#detect_cont(img)
cv2.namedWindow("TrackBars")
cv2.resizeWindow("TrackBars", 640, 240)
cv2.createTrackbar("Min", "TrackBars", 50, 300, empty)
cv2.createTrackbar("Max", "TrackBars", 50, 300, empty)

cv2.namedWindow("preview")
vc = cv2.VideoCapture(cv2.CAP_DSHOW)
vc.set(cv2.CAP_PROP_FRAME_HEIGHT, 240)
vc.set(cv2.CAP_PROP_FRAME_WIDTH, 320)
vc.set(cv2.CAP_PROP_FOURCC, 0x32595559)
vc.set(10, 150)
vc.set(cv2.CAP_PROP_FPS, 20)

if vc.isOpened():  # try to get the first frame
    rval, frame = vc.read()
else:
    rval = False

running, frame = vc.read()

good = 1
bad = 1

while rval:
    cv2.imshow("preview", frame)

    pos_min = cv2.getTrackbarPos("Min", "TrackBars")
    pos_max = cv2.getTrackbarPos("Max", "TrackBars")

    img_final, imgContours = detect_cont(frame, pos_min, pos_max)
    #cv2.imshow("Tons de Cinza", img_final)
    cv2.imshow("Densenhado", imgContours)

    rval, frame = vc.read()
    key = cv2.waitKey(20)

    if key == 27:  # exit on ESC
        break

    if key & 0xFF == ord("q"):
        running = False

vc.release()
cv2.destroyWindow("preview")

Machined Part



source https://stackoverflow.com/questions/72353750/how-can-i-identify-a-roi-that-is-formed-by-many-contours-canny-image-opencv

Comments

Popular posts from this blog

Prop `className` did not match in next js app

I have written a sample code ( Github Link here ). this is a simple next js app, but giving me error when I refresh the page. This seems to be the common problem and I tried the fix provided in the internet but does not seem to fix my issue. The error is Warning: Prop className did not match. Server: "MuiBox-root MuiBox-root-1" Client: "MuiBox-root MuiBox-root-2". Did changes for _document.js, modified _app.js as mentioned in official website and solutions in stackoverflow. but nothing seems to work. Could someone take a look and help me whats wrong with the code? Via Active questions tagged javascript - Stack Overflow https://ift.tt/2FdjaAW

How to show number of registered users in Laravel based on usertype?

i'm trying to display data from the database in the admin dashboard i used this: <?php use Illuminate\Support\Facades\DB; $users = DB::table('users')->count(); echo $users; ?> and i have successfully get the correct data from the database but what if i want to display a specific data for example in this user table there is "usertype" that specify if the user is normal user or admin i want to user the same code above but to display a specific usertype i tried this: <?php use Illuminate\Support\Facades\DB; $users = DB::table('users')->count()->WHERE usertype =admin; echo $users; ?> but it didn't work, what am i doing wrong? source https://stackoverflow.com/questions/68199726/how-to-show-number-of-registered-users-in-laravel-based-on-usertype

Why is my reports service not connecting?

I am trying to pull some data from a Postgres database using Node.js and node-postures but I can't figure out why my service isn't connecting. my routes/index.js file: const express = require('express'); const router = express.Router(); const ordersCountController = require('../controllers/ordersCountController'); const ordersController = require('../controllers/ordersController'); const weeklyReportsController = require('../controllers/weeklyReportsController'); router.get('/orders_count', ordersCountController); router.get('/orders', ordersController); router.get('/weekly_reports', weeklyReportsController); module.exports = router; My controllers/weeklyReportsController.js file: const weeklyReportsService = require('../services/weeklyReportsService'); const weeklyReportsController = async (req, res) => { try { const data = await weeklyReportsService; res.json({data}) console